© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1608
    Prev
    Next
    INDEX
    Explanations

    book and journal publication information (city, publisher, date).

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    曖昧さ回避
    -0.75
    ⓧ
    -0.73
    
    -0.68
     Letter
    -0.65
     jScrollPane
    -0.63
     letters
    -0.62
     Letters
    -0.62
     fallu
    -0.62
    stdc
    -0.61
     letter
    -0.59
    POSITIVE LOGITS
     ISBN
    0.67
     second
    0.61
    second
    0.57
    ISBN
    0.54
     third
    0.53
    ніципа
    0.52
     Edition
    0.50
     edition
    0.49
     ed
    0.49
    Second
    0.48
    Activations Density 0.385%

    No Known Activations